End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +857 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: llama3-1_8b_physics_500000_samples
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# llama3-1_8b_physics_500000_samples
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.7704
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: llama3-1_8b_physics_500000_samples
|
|
|
|
| 16 |
|
| 17 |
# llama3-1_8b_physics_500000_samples
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/physics_500000_samples dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.7704
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.7703806757926941,
|
| 4 |
+
"eval_runtime": 35.766,
|
| 5 |
+
"eval_samples_per_second": 284.46,
|
| 6 |
+
"eval_steps_per_second": 1.118,
|
| 7 |
+
"total_flos": 1899492236328960.0,
|
| 8 |
+
"train_loss": 0.7598387925923397,
|
| 9 |
+
"train_runtime": 7118.4294,
|
| 10 |
+
"train_samples_per_second": 81.465,
|
| 11 |
+
"train_steps_per_second": 0.159
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.7703806757926941,
|
| 4 |
+
"eval_runtime": 35.766,
|
| 5 |
+
"eval_samples_per_second": 284.46,
|
| 6 |
+
"eval_steps_per_second": 1.118
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1899492236328960.0,
|
| 4 |
+
"train_loss": 0.7598387925923397,
|
| 5 |
+
"train_runtime": 7118.4294,
|
| 6 |
+
"train_samples_per_second": 81.465,
|
| 7 |
+
"train_steps_per_second": 0.159
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,857 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1134,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.026455026455026454,
|
| 13 |
+
"grad_norm": 7.5692021410659995,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0155,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05291005291005291,
|
| 20 |
+
"grad_norm": 2.6174349537450885,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.9187,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07936507936507936,
|
| 27 |
+
"grad_norm": 2.793450551829053,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.8889,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.10582010582010581,
|
| 34 |
+
"grad_norm": 1.0752828617491306,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.8728,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13227513227513227,
|
| 41 |
+
"grad_norm": 0.7890229586623537,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.8553,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15873015873015872,
|
| 48 |
+
"grad_norm": 0.8515898940332954,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.8472,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18518518518518517,
|
| 55 |
+
"grad_norm": 0.6739899043810001,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.8386,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.21164021164021163,
|
| 62 |
+
"grad_norm": 0.7472386351456437,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.8303,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.23809523809523808,
|
| 69 |
+
"grad_norm": 0.8201164599585603,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.8296,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.26455026455026454,
|
| 76 |
+
"grad_norm": 0.5974248203060147,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.8208,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.291005291005291,
|
| 83 |
+
"grad_norm": 0.7418126551089665,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.817,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.31746031746031744,
|
| 90 |
+
"grad_norm": 0.8971788447098652,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.816,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3439153439153439,
|
| 97 |
+
"grad_norm": 0.6659038218094219,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.8095,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.37037037037037035,
|
| 104 |
+
"grad_norm": 0.8687534608310304,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.809,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3968253968253968,
|
| 111 |
+
"grad_norm": 0.6997183066642144,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.8116,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.42328042328042326,
|
| 118 |
+
"grad_norm": 0.6784743741082218,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.8043,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.4497354497354497,
|
| 125 |
+
"grad_norm": 0.8279542209712195,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.8081,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.47619047619047616,
|
| 132 |
+
"grad_norm": 0.6448467413029932,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.806,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5026455026455027,
|
| 139 |
+
"grad_norm": 0.5414700848521968,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.8021,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5291005291005291,
|
| 146 |
+
"grad_norm": 0.6833581882793117,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.7978,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5555555555555556,
|
| 153 |
+
"grad_norm": 0.9216374614283346,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.7997,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.582010582010582,
|
| 160 |
+
"grad_norm": 0.6017660770757399,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.7942,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6084656084656085,
|
| 167 |
+
"grad_norm": 0.6412167679844537,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.791,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6349206349206349,
|
| 174 |
+
"grad_norm": 0.6772848668775633,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.7948,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6613756613756614,
|
| 181 |
+
"grad_norm": 0.600355639535383,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.7914,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6878306878306878,
|
| 188 |
+
"grad_norm": 0.5606573561606166,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.7941,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7142857142857143,
|
| 195 |
+
"grad_norm": 0.5274683257315145,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.7934,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7407407407407407,
|
| 202 |
+
"grad_norm": 0.5268307259184533,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.7938,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7671957671957672,
|
| 209 |
+
"grad_norm": 0.7728039906376213,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.7917,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7936507936507936,
|
| 216 |
+
"grad_norm": 0.5113816020074538,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.7882,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.8201058201058201,
|
| 223 |
+
"grad_norm": 0.5190008909833674,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.7849,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8465608465608465,
|
| 230 |
+
"grad_norm": 0.5836368027639713,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.7884,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.873015873015873,
|
| 237 |
+
"grad_norm": 0.7393083910981807,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.7832,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8994708994708994,
|
| 244 |
+
"grad_norm": 0.6790621837196994,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.7889,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9259259259259259,
|
| 251 |
+
"grad_norm": 0.7554140140474603,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.7915,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9523809523809523,
|
| 258 |
+
"grad_norm": 0.5810605450609724,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.7863,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9788359788359788,
|
| 265 |
+
"grad_norm": 0.6061224991845839,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.7836,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.0,
|
| 272 |
+
"eval_loss": 0.7853822112083435,
|
| 273 |
+
"eval_runtime": 36.7907,
|
| 274 |
+
"eval_samples_per_second": 276.537,
|
| 275 |
+
"eval_steps_per_second": 1.087,
|
| 276 |
+
"step": 378
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.0052910052910053,
|
| 280 |
+
"grad_norm": 0.8837267831248354,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.7782,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.0317460317460316,
|
| 287 |
+
"grad_norm": 0.8327957648034358,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.752,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0582010582010581,
|
| 294 |
+
"grad_norm": 0.7661996686677544,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.7504,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.0846560846560847,
|
| 301 |
+
"grad_norm": 0.574247744750553,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.753,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.1111111111111112,
|
| 308 |
+
"grad_norm": 0.6270570009050412,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.7526,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.1375661375661377,
|
| 315 |
+
"grad_norm": 0.7564791753598593,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.7499,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.164021164021164,
|
| 322 |
+
"grad_norm": 0.6019767178166228,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.7534,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1904761904761905,
|
| 329 |
+
"grad_norm": 0.7045276656881013,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.7516,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.216931216931217,
|
| 336 |
+
"grad_norm": 0.7151521174595956,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.7525,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.2433862433862433,
|
| 343 |
+
"grad_norm": 0.8589885709685776,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.7506,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2698412698412698,
|
| 350 |
+
"grad_norm": 0.8448779205925924,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.7529,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.2962962962962963,
|
| 357 |
+
"grad_norm": 0.698173785850267,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.7523,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.3227513227513228,
|
| 364 |
+
"grad_norm": 0.5810999760014718,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.7493,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3492063492063493,
|
| 371 |
+
"grad_norm": 0.6992760350263512,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.7468,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3756613756613756,
|
| 378 |
+
"grad_norm": 0.6741207559975058,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.7498,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.402116402116402,
|
| 385 |
+
"grad_norm": 0.5507423746197616,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.7523,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.4285714285714286,
|
| 392 |
+
"grad_norm": 0.6210883025743585,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.7491,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.455026455026455,
|
| 399 |
+
"grad_norm": 0.5352886813564971,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.7501,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4814814814814814,
|
| 406 |
+
"grad_norm": 0.6312193974549839,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.7523,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.507936507936508,
|
| 413 |
+
"grad_norm": 0.5240777963700096,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.7506,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.5343915343915344,
|
| 420 |
+
"grad_norm": 0.6713658440893504,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.7498,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.560846560846561,
|
| 427 |
+
"grad_norm": 0.5581636551389646,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.749,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.5873015873015874,
|
| 434 |
+
"grad_norm": 0.5510394311493787,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.7507,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.6137566137566137,
|
| 441 |
+
"grad_norm": 0.7490035349717284,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.751,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.6402116402116402,
|
| 448 |
+
"grad_norm": 0.7019577853473584,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.7452,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.6666666666666665,
|
| 455 |
+
"grad_norm": 0.5188517209828246,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.747,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.693121693121693,
|
| 462 |
+
"grad_norm": 0.5852910158185847,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.7478,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.7195767195767195,
|
| 469 |
+
"grad_norm": 0.5163509954560109,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.7493,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.746031746031746,
|
| 476 |
+
"grad_norm": 0.5259629378155002,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.7488,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.7724867724867726,
|
| 483 |
+
"grad_norm": 0.5847699777528805,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.7484,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.798941798941799,
|
| 490 |
+
"grad_norm": 0.6909699114073832,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.7425,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.8253968253968254,
|
| 497 |
+
"grad_norm": 0.5026266608814028,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.7481,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.8518518518518519,
|
| 504 |
+
"grad_norm": 0.4905863322036327,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.7427,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.8783068783068781,
|
| 511 |
+
"grad_norm": 0.4940567635795736,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.7468,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.9047619047619047,
|
| 518 |
+
"grad_norm": 0.5002276189718439,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.7411,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.9312169312169312,
|
| 525 |
+
"grad_norm": 0.5990930220626486,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.7445,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.9576719576719577,
|
| 532 |
+
"grad_norm": 0.575362618033918,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.746,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.9841269841269842,
|
| 539 |
+
"grad_norm": 0.5971817140113224,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.7439,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.0,
|
| 546 |
+
"eval_loss": 0.7724016904830933,
|
| 547 |
+
"eval_runtime": 36.4294,
|
| 548 |
+
"eval_samples_per_second": 279.28,
|
| 549 |
+
"eval_steps_per_second": 1.098,
|
| 550 |
+
"step": 756
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.0105820105820107,
|
| 554 |
+
"grad_norm": 0.7946153532333404,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.7315,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.037037037037037,
|
| 561 |
+
"grad_norm": 0.6230352829055962,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.7084,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.0634920634920633,
|
| 568 |
+
"grad_norm": 0.6511688564166924,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.7103,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.0899470899470898,
|
| 575 |
+
"grad_norm": 0.6162972908978676,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.7106,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.1164021164021163,
|
| 582 |
+
"grad_norm": 0.5483322240242068,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.7103,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.142857142857143,
|
| 589 |
+
"grad_norm": 0.5167695346041687,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.7118,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.1693121693121693,
|
| 596 |
+
"grad_norm": 0.5731147019555838,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.7117,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.195767195767196,
|
| 603 |
+
"grad_norm": 0.5992340825814363,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.7115,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.2222222222222223,
|
| 610 |
+
"grad_norm": 0.8204374260544979,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.7116,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.248677248677249,
|
| 617 |
+
"grad_norm": 0.6452436861380945,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.7132,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.2751322751322753,
|
| 624 |
+
"grad_norm": 0.7905676999430032,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.7156,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.3015873015873014,
|
| 631 |
+
"grad_norm": 0.6453047673638057,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.7134,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.328042328042328,
|
| 638 |
+
"grad_norm": 0.6161389768819914,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.7182,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.3544973544973544,
|
| 645 |
+
"grad_norm": 0.5925752010088033,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.7152,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.380952380952381,
|
| 652 |
+
"grad_norm": 0.5465043223339282,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.7164,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.4074074074074074,
|
| 659 |
+
"grad_norm": 0.5991686328257099,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.7169,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.433862433862434,
|
| 666 |
+
"grad_norm": 0.5529948466057861,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.7134,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.4603174603174605,
|
| 673 |
+
"grad_norm": 0.5700704291829093,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.714,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.4867724867724865,
|
| 680 |
+
"grad_norm": 0.7107367519714186,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.7119,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.5132275132275135,
|
| 687 |
+
"grad_norm": 0.5145994918143386,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.7164,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.5396825396825395,
|
| 694 |
+
"grad_norm": 0.8526143229072503,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.7176,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.566137566137566,
|
| 701 |
+
"grad_norm": 0.6460058195221838,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.718,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.5925925925925926,
|
| 708 |
+
"grad_norm": 0.5722175187803165,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.7158,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.619047619047619,
|
| 715 |
+
"grad_norm": 0.6199806409264405,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.7152,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.6455026455026456,
|
| 722 |
+
"grad_norm": 0.6295374166579548,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.7167,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.671957671957672,
|
| 729 |
+
"grad_norm": 0.5562186015106506,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.7143,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.6984126984126986,
|
| 736 |
+
"grad_norm": 0.5802340156160444,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.7201,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.7248677248677247,
|
| 743 |
+
"grad_norm": 0.5674240362878424,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.7151,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.751322751322751,
|
| 750 |
+
"grad_norm": 0.5579240804629998,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.7113,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.7777777777777777,
|
| 757 |
+
"grad_norm": 0.5511568456212458,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.7153,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.804232804232804,
|
| 764 |
+
"grad_norm": 0.53261750815606,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.7147,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.8306878306878307,
|
| 771 |
+
"grad_norm": 0.601473528074606,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.7165,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.857142857142857,
|
| 778 |
+
"grad_norm": 0.4922870741419976,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.7147,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.8835978835978837,
|
| 785 |
+
"grad_norm": 0.5647388229398058,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.7146,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.91005291005291,
|
| 792 |
+
"grad_norm": 0.6422541209526703,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.7175,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.9365079365079367,
|
| 799 |
+
"grad_norm": 0.6977559447017284,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.7162,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.962962962962963,
|
| 806 |
+
"grad_norm": 0.7941392765996913,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.714,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.9894179894179893,
|
| 813 |
+
"grad_norm": 0.6766160989486909,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.7146,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.0,
|
| 820 |
+
"eval_loss": 0.7703806757926941,
|
| 821 |
+
"eval_runtime": 35.7626,
|
| 822 |
+
"eval_samples_per_second": 284.487,
|
| 823 |
+
"eval_steps_per_second": 1.118,
|
| 824 |
+
"step": 1134
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.0,
|
| 828 |
+
"step": 1134,
|
| 829 |
+
"total_flos": 1899492236328960.0,
|
| 830 |
+
"train_loss": 0.7598387925923397,
|
| 831 |
+
"train_runtime": 7118.4294,
|
| 832 |
+
"train_samples_per_second": 81.465,
|
| 833 |
+
"train_steps_per_second": 0.159
|
| 834 |
+
}
|
| 835 |
+
],
|
| 836 |
+
"logging_steps": 10,
|
| 837 |
+
"max_steps": 1134,
|
| 838 |
+
"num_input_tokens_seen": 0,
|
| 839 |
+
"num_train_epochs": 3,
|
| 840 |
+
"save_steps": 500,
|
| 841 |
+
"stateful_callbacks": {
|
| 842 |
+
"TrainerControl": {
|
| 843 |
+
"args": {
|
| 844 |
+
"should_epoch_stop": false,
|
| 845 |
+
"should_evaluate": false,
|
| 846 |
+
"should_log": false,
|
| 847 |
+
"should_save": true,
|
| 848 |
+
"should_training_stop": true
|
| 849 |
+
},
|
| 850 |
+
"attributes": {}
|
| 851 |
+
}
|
| 852 |
+
},
|
| 853 |
+
"total_flos": 1899492236328960.0,
|
| 854 |
+
"train_batch_size": 16,
|
| 855 |
+
"trial_name": null,
|
| 856 |
+
"trial_params": null
|
| 857 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|